Commit ·
c5ea432
1
Parent(s): 79c1f3c
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: PSST_spell_correction_V3
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# PSST_spell_correction_V3
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.5390
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 1e-05
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 30
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 48 |
+
| 0.3418 | 1.0 | 3099 | 0.3206 |
|
| 49 |
+
| 0.2821 | 2.0 | 6198 | 0.3216 |
|
| 50 |
+
| 0.2467 | 3.0 | 9297 | 0.3501 |
|
| 51 |
+
| 0.2301 | 4.0 | 12396 | 0.3747 |
|
| 52 |
+
| 0.2152 | 5.0 | 15495 | 0.3614 |
|
| 53 |
+
| 0.2071 | 6.0 | 18594 | 0.3836 |
|
| 54 |
+
| 0.2002 | 7.0 | 21693 | 0.3923 |
|
| 55 |
+
| 0.1964 | 8.0 | 24792 | 0.4053 |
|
| 56 |
+
| 0.1953 | 9.0 | 27891 | 0.4154 |
|
| 57 |
+
| 0.1935 | 10.0 | 30990 | 0.4269 |
|
| 58 |
+
| 0.1918 | 11.0 | 34089 | 0.4381 |
|
| 59 |
+
| 0.1889 | 12.0 | 37188 | 0.4623 |
|
| 60 |
+
| 0.1886 | 13.0 | 40287 | 0.4586 |
|
| 61 |
+
| 0.1869 | 14.0 | 43386 | 0.4838 |
|
| 62 |
+
| 0.1867 | 15.0 | 46485 | 0.4984 |
|
| 63 |
+
| 0.1857 | 16.0 | 49584 | 0.4623 |
|
| 64 |
+
| 0.1843 | 17.0 | 52683 | 0.5020 |
|
| 65 |
+
| 0.1834 | 18.0 | 55782 | 0.5129 |
|
| 66 |
+
| 0.1832 | 19.0 | 58881 | 0.4972 |
|
| 67 |
+
| 0.1835 | 20.0 | 61980 | 0.4895 |
|
| 68 |
+
| 0.1822 | 21.0 | 65079 | 0.4992 |
|
| 69 |
+
| 0.1834 | 22.0 | 68178 | 0.5291 |
|
| 70 |
+
| 0.1816 | 23.0 | 71277 | 0.5351 |
|
| 71 |
+
| 0.1802 | 24.0 | 74376 | 0.5294 |
|
| 72 |
+
| 0.1796 | 25.0 | 77475 | 0.5443 |
|
| 73 |
+
| 0.1814 | 26.0 | 80574 | 0.5368 |
|
| 74 |
+
| 0.1804 | 27.0 | 83673 | 0.5375 |
|
| 75 |
+
| 0.1811 | 28.0 | 86772 | 0.5435 |
|
| 76 |
+
| 0.1811 | 29.0 | 89871 | 0.5391 |
|
| 77 |
+
| 0.1802 | 30.0 | 92970 | 0.5390 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.28.0
|
| 83 |
+
- Pytorch 1.12.1+cu102
|
| 84 |
+
- Datasets 2.13.1
|
| 85 |
+
- Tokenizers 0.13.3
|